Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM

Mobina Ezzoddin; Hamid Nasiri; Morteza Dorrigiv

doi:10.1109/MVIP53647.2022.9738760

Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM

Mobina Ezzoddin, Hamid Nasiri, Morteza Dorrigiv

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

16 Citations (Scopus)

Abstract

The Coronavirus was detected in Wuhan, China in late 2019 and then led to a pandemic with a rapid worldwide outbreak. The number of infected people has been swiftly increasing since then. Therefore, in this study, an attempt was made to propose a new and efficient method for automatic diagnosis of Corona disease from X-ray images using Deep Neural Networks (DNNs). In the proposed method, the DensNet169 was used to extract the features of the patients' Chest X-Ray (CXR) images. The extracted features were given to a feature selection algorithm (i.e., ANOVA) to select a number of them. Finally, the selected features were classified by LightGBM algorithm. The proposed approach was evaluated on the ChestX-ray8 dataset and reached 99.20% and 94.22% accuracies in the two-class (i.e., COVID-19 and No-findings) and multi-class (i.e., COVID-19, Pneumonia, and No-findings) classification problems, respectively.

Original language	English
Title of host publication	Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022
Publisher	IEEE Computer Society
Number of pages	7
ISBN (Electronic)	9781665412162
ISBN (Print)	9781665412179
DOIs	https://doi.org/10.1109/MVIP53647.2022.9738760
Publication status	Published - 22 Mar 2022
Externally published	Yes
Event	12th Iranian/2nd International Conference on Machine Vision and Image Processing - Ahvaz, Iran, Islamic Republic of Duration: 23 Feb 2022 → 24 Feb 2022 https://web.archive.org/web/20220209144207/http://mvip2022.ismvipconf.ir/

Publication series

Name	Iranian Conference on Machine Vision and Image Processing, MVIP
Publisher	IEEE
Volume	2022-February
ISSN (Print)	2166-6776
ISSN (Electronic)	2166-6784

Conference

Conference	12th Iranian/2nd International Conference on Machine Vision and Image Processing
Abbreviated title	MVIP 2022
Country/Territory	Iran, Islamic Republic of
City	Ahvaz
Period	23/02/22 → 24/02/22
Internet address	https://web.archive.org/web/20220209144207/http://mvip2022.ismvipconf.ir/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/MVIP53647.2022.9738760Licence: Unspecified

Cite this

Ezzoddin, M., Nasiri, H., & Dorrigiv, M. (2022). Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM. In Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022 Article 9738760 (Iranian Conference on Machine Vision and Image Processing, MVIP; Vol. 2022-February). IEEE Computer Society. https://doi.org/10.1109/MVIP53647.2022.9738760

@inproceedings{cc18353633734f9996eb8115ed921d0b,

title = "Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM",

abstract = "The Coronavirus was detected in Wuhan, China in late 2019 and then led to a pandemic with a rapid worldwide outbreak. The number of infected people has been swiftly increasing since then. Therefore, in this study, an attempt was made to propose a new and efficient method for automatic diagnosis of Corona disease from X-ray images using Deep Neural Networks (DNNs). In the proposed method, the DensNet169 was used to extract the features of the patients' Chest X-Ray (CXR) images. The extracted features were given to a feature selection algorithm (i.e., ANOVA) to select a number of them. Finally, the selected features were classified by LightGBM algorithm. The proposed approach was evaluated on the ChestX-ray8 dataset and reached 99.20\% and 94.22\% accuracies in the two-class (i.e., COVID-19 and No-findings) and multi-class (i.e., COVID-19, Pneumonia, and No-findings) classification problems, respectively.",

keywords = "ANOVA, Chest X-ray Images, Coronavirus, COVID-19, DenseNet169, LightGBM",

author = "Mobina Ezzoddin and Hamid Nasiri and Morteza Dorrigiv",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022 ; Conference date: 23-02-2022 Through 24-02-2022",

year = "2022",

month = mar,

day = "22",

doi = "10.1109/MVIP53647.2022.9738760",

language = "English",

isbn = "9781665412179",

series = "Iranian Conference on Machine Vision and Image Processing, MVIP",

publisher = "IEEE Computer Society",

booktitle = "Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022",

address = "United States",

url = "https://web.archive.org/web/20220209144207/http://mvip2022.ismvipconf.ir/",

}

Ezzoddin, M, Nasiri, H & Dorrigiv, M 2022, Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM. in Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022., 9738760, Iranian Conference on Machine Vision and Image Processing, MVIP, vol. 2022-February, IEEE Computer Society, 12th Iranian/2nd International Conference on Machine Vision and Image Processing, Ahvaz, Iran, Islamic Republic of, 23/02/22. https://doi.org/10.1109/MVIP53647.2022.9738760

Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM. / Ezzoddin, Mobina; Nasiri, Hamid; Dorrigiv, Morteza.
Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022. IEEE Computer Society, 2022. 9738760 (Iranian Conference on Machine Vision and Image Processing, MVIP; Vol. 2022-February).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM

AU - Ezzoddin, Mobina

AU - Nasiri, Hamid

AU - Dorrigiv, Morteza

PY - 2022/3/22

Y1 - 2022/3/22

N2 - The Coronavirus was detected in Wuhan, China in late 2019 and then led to a pandemic with a rapid worldwide outbreak. The number of infected people has been swiftly increasing since then. Therefore, in this study, an attempt was made to propose a new and efficient method for automatic diagnosis of Corona disease from X-ray images using Deep Neural Networks (DNNs). In the proposed method, the DensNet169 was used to extract the features of the patients' Chest X-Ray (CXR) images. The extracted features were given to a feature selection algorithm (i.e., ANOVA) to select a number of them. Finally, the selected features were classified by LightGBM algorithm. The proposed approach was evaluated on the ChestX-ray8 dataset and reached 99.20% and 94.22% accuracies in the two-class (i.e., COVID-19 and No-findings) and multi-class (i.e., COVID-19, Pneumonia, and No-findings) classification problems, respectively.

AB - The Coronavirus was detected in Wuhan, China in late 2019 and then led to a pandemic with a rapid worldwide outbreak. The number of infected people has been swiftly increasing since then. Therefore, in this study, an attempt was made to propose a new and efficient method for automatic diagnosis of Corona disease from X-ray images using Deep Neural Networks (DNNs). In the proposed method, the DensNet169 was used to extract the features of the patients' Chest X-Ray (CXR) images. The extracted features were given to a feature selection algorithm (i.e., ANOVA) to select a number of them. Finally, the selected features were classified by LightGBM algorithm. The proposed approach was evaluated on the ChestX-ray8 dataset and reached 99.20% and 94.22% accuracies in the two-class (i.e., COVID-19 and No-findings) and multi-class (i.e., COVID-19, Pneumonia, and No-findings) classification problems, respectively.

KW - ANOVA

KW - Chest X-ray Images

KW - Coronavirus

KW - COVID-19

KW - DenseNet169

KW - LightGBM

UR - https://www.scopus.com/pages/publications/85127450421

U2 - 10.1109/MVIP53647.2022.9738760

DO - 10.1109/MVIP53647.2022.9738760

M3 - Conference contribution

AN - SCOPUS:85127450421

SN - 9781665412179

T3 - Iranian Conference on Machine Vision and Image Processing, MVIP

BT - Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022

PB - IEEE Computer Society

T2 - 12th Iranian/2nd International Conference on Machine Vision and Image Processing

Y2 - 23 February 2022 through 24 February 2022

ER -

Ezzoddin M, Nasiri H, Dorrigiv M. Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM. In Proceedings of 2022 12th Iranian/2nd International Conference on Machine Vision and Image Processing, MVIP 2022. IEEE Computer Society. 2022. 9738760. (Iranian Conference on Machine Vision and Image Processing, MVIP). doi: 10.1109/MVIP53647.2022.9738760

Diagnosis of COVID-19 Cases from Chest X-ray Images Using Deep Neural Network and LightGBM

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this